Engineering Manager Agentic AI

Job Summary

Who We Are

Were an iconic Aussie brand with a global footprint. Our purpose is to build a connected future so everyone can thrive. Were all about providing the best experience and delivering the best tech on the best network.

This includes making Telstra the place you want to work. For you that means a having career that grows with you and working with a team powered by human connection that prioritises wellbeing and choice.

What is the focus of the role

The Agentic AI Engineer / Chapter Lead combines hands-on AI engineering depth with chapter leadership. The role designs builds and operates secure reliable and cost-effective agentic AI solutions while developing engineering capability and establishing reusable patterns standards and reference implementations.

The role works across backend platform product architecture security and SRE teams to move LLM solutions from prototype to governed production use on AWS with accountability for technical quality responsible AI and sustainable adoption of AI-assisted engineering practices.

What we offer

• Performance-related pay
• Access to thousands of learning programs so you can level-up
• Global presence across 22 countries; opportunities to work where we do business.
• Up to 26 weeks maternity leave provided to the birth mother with benefits for all child births
• Up to 16 weeks paid paternity leave provided to the non-birthing partners
• Employees are entitled to 21 paid annual leaves per calendar year
• Eligible employees are entitled to 12 days of paid sick / casual leave per calendar year
• Relocation support options across India from junior to senior positions within the company
• Receive insurance benefits such as medical accidental and life insurances

Design build and operate single-agent and multi-agent systems using LangGraph Amazon Bedrock Agents and appropriate direct SDK approaches.

Define agent workflows state checkpointing human-in-the-loop controls tool schemas contracts boundaries and safe hand-off patterns.

Apply engineering judgement to determine when agent frameworks are required and when simpler deterministic or direct model integration is better.

Design and tune RAG and agentic RAG pipelines across approved enterprise knowledge sources including ingestion retrieval indexing re-ranking and grounding.

Implement hybrid retrieval query planning self-correction and tool-augmented retrieval patterns to improve relevance and task completion.

Evaluate vector stores and knowledge graph or GraphRAG approaches where scale security cost or relationship-heavy domains require them.

Build and operate MCP servers and clients including tools resources prompts and supported transports.

Expose secure capabilities with clear descriptions validation versioning least-privilege access and defined trust boundaries.

Apply agent-to-agent concepts such as discovery agent cards task lifecycle collaboration and capability registration.

Create evaluation frameworks using golden datasets deterministic checks LLM-as-judge techniques human review and regression suites.

Integrate quality safety groundedness latency token usage and cost gates into delivery and release processes.

Benchmark models and architectures for quality reliability throughput context requirements and total cost.

Build security privacy safety guardrails and governance into agentic solutions from inception.

Mitigate risks including prompt injection data leakage excessive agency unsafe tool use insecure output handling and supply-chain exposure.

Implement PII handling scoped identity OAuth where applicable secret management least-privilege access human approval and audit trails for sensitive actions.

Apply data residency retention privacy versioning hallucination and bias risk assessment change control and responsible AI requirements.

Build AI services using strong Python practices including asynchronous programming FastAPI automated testing and maintainable package design.

Deploy and operate services on AWS and Kubernetes with CI/CD secure runtime configuration and operational controls.

Instrument agent systems with tracing logging metrics and evaluation telemetry using OpenTelemetry and relevant LLM observability platforms.

Implement reliability patterns including timeouts retries fallbacks failover rate limits concurrency controls and graceful degradation.

Treat prompts agent definitions evaluation datasets policies and configuration as versioned reviewed and tested engineering artefacts.

Actively build chapter capability by mentoring engineers in software engineering practices emerging technologies tools approaches and delivery processes modelling continuous learning and coaching others to lift capability across teams.

Coach develop and provide regular feedback to chapter members clarifying performance behavioural and engineering expectations and supporting meaningful growth conversations.

Build strong commercial capability across teams by modelling disciplined cost-value thinking balancing engineering investment platform cost risk and customer outcomes to choose the most economic course of action.

Foster a culture of observability across multiple teams helping engineers use operational telemetry service health data incident trends and customer-impact signals to improve stability performance and domain ownership.

Influence effective decision-making in uncertain or high-pressure situations making responsible trade-offs without always having complete information and helping teams manage risk change and ambiguity.

Build a strong culture of knowledge sharing documentation and constructive feedback using communities of practice playbooks reference patterns and learning forums to drive continuous improvement and capability uplift.

Model Telstras values and facilitate inclusive discussions across teams creating alignment to organisational strategy and principles while identifying actionable continuous improvement opportunities.

Manage recruitment of permanent employees and partner resources shaping a healthy workforce plan succession pipeline and highly productive team mix aligned to current and future capability needs.

Set goals and lead performance appraisal for engineers ensuring expectations outcomes development needs and accountability are clearly understood and fairly assessed.

Ensure co-workers are treated respectfully and without discrimination harassment or victimisation actively contributing to psychological safety inclusion and a respectful workplace.

Assess AI and modern engineering capability needs align people to priority work and support safe adoption of AI-assisted engineering tools spec-driven development and reusable standards.

Balance hands-on technical leadership with people accountability chapter health resource planning and delivery commitments.

About You

Required Skills and Technical Expertise

• Agentic AI architecture orchestration LLM prompt and context engineering.
• RAG agentic RAG enterprise knowledge systems MCP and agent-to-agent communication.
• AI evaluation model selection token economics quality gates and responsible AI practices.
• AI security governance privacy guardrails risk controls and safe production deployment.
• Strong production engineering across Python AWS Kubernetes CI/CD observability reliability and operations.
• Technical leadership stakeholder influence coaching workforce capability uplift and reusable engineering standards.
• undefined

Qualifications and Experience

• 10 years professional software engineering experience including 2 years building LLM-based applications or equivalent production AI depth.
• Experience taking agentic or generative AI solutions from discovery and prototype to production operation.
• Experience leading technical outcomes across teams and coaching engineers in emerging technologies.
• Degree in Computer Science Software Engineering Artificial Intelligence Data Science or related discipline or equivalent relevant experience.

Preferred Skills

• Integration of AI capabilities with Java Spring Boot or services using Spring AI LangChain4j or comparable libraries.
• Fine-tuning or parameter-efficient adaptation including LoRA.
• Experience with additional agent frameworks such as Strands Agents CrewAI OpenAI Agents SDK or Claude Agent SDK.
• Background in SRE platform engineering event-driven architecture Kafka or Redis Streams.
• Contributions to AI tooling internal engineering communities or relevant cloud and AI certifications.
• Experience with enterprise model gateways agent registries AI inventory governance platforms or internally hosted model ecosystems.
• End-to-end solution design from chat UI through orchestration retrieval tool execution and LLM response delivery including clear ownership of user experience backend services and model interaction patterns.
• Understanding of A2UI A2A and shared UI communication practices including how agents user interfaces and backend services coordinate context actions state and hand-offs safely across a shared experience.

Were amongst the top 2% of companies globally in the CDP Global Climate Change Index 2023 being awarded an A rating. If you want to work for a company that cares about sustainability we want to hear from you.

As part of your application with Telstra you may receive communications from us on(for job applications in Australia) and 1 (for job applications in the Philippines and India).

When you join our team you become part of a welcoming and inclusive community where everyone is respected valued and celebrated. We actively seek individuals from various backgrounds ethnicities genders and disabilities because we know that diversity not only strengthens our team but also enriches our work. We have zero tolerance for harassment of any kind and we prioritise creating a workplace culture where everyone is safe and can thrive.

As part of the hiring process all identified candidates will undergo a background check and the results will play a role in the final decision regarding your application.

We work flexibly at Telstra. Talk to us about what flexibility means to you. When you apply you can share your pronouns and / or any reasonable adjustments needed to take part equitably during the recruitment process.

We are aware of current limitations with our website accessibility and are working towards improving this. Should you experience any issues accessing information or the application form and require this in an alternate format please contact our Talent Acquisition team on or via the additional contact options found at Experience:

Manager