AI Tech Lead AI Engineer

We are seeking a high-caliber AI Tech Lead / AI Engineer to design build and operationalize agentic AI solutions that accelerate analytics and reporting delivery. This role goes beyond basic agent creation and requires hands-on experience with agent orchestration memory and enterprise-grade data access patterns delivering scalable components that fit into an existing framework while rapidly adapting to incoming business requests.

Responsibilities: -

• Design Architect implement and iterate on agentic AI solutions to shorten the cycle time for analytics log analysis and reporting requests.
• Design agent orchestration patterns (multi-agent workflows) tool/function calling and memory approaches appropriate for enterprise deployments.
• Define secure and scalable data access patterns for agents (retrieval context building and grounding) integrating with existing data sources and governance expectations.
• Partner closely with product analytics and engineering stakeholders to intake requirements quickly and deliver working prototypes and production-ready solutions.
• Engineer reusable components and best practices that enable scalable delivery (not one-off scripts) aligned to an existing base framework.
• Operationalize solutions for reliability and maintainability: testing strategies monitoring/observability prompt/version management and deployment automation.
• Evaluate build vs. buy options pragmatically when needed while keeping focus on shipping solutions on the current platform stack.

Tech Stack (Core): -

• Cloud: AWS (primary deployment environment; open to alternatives)
• Data/Analytics Platform: Databricks (including native chat with data capabilities and potential agent integrations)
• Agent Frameworks: LangChain LangGraph
• Conversational analytics patterns: Ask-questions-on-data / conversational BI approaches (agent-driven analytics and dashboards

Experience: -

10 Years

Location: -

Rosemont IL (3days/Week)

Educational Qualifications: -

Engineering Degree BE/ME/BTech/MTech/BSc/MSc.

Technical certification in multiple technologies is desirable.

Skills: -

Mandatory skills

• Demonstrated experience delivering agentic AI solutions beyond prototypes including enterprise deployment considerations.
• Strong hands-on engineering background with AWS-based deployments.
• Experience working with modern data platforms (e.g. Databricks) and integrating LLM solutions with analytics/data ecosystems.
• Ability to operate as a senior individual contributor who can define architecture and implement key pieces end-to-end.

Excellent communication and collaboration skills with US-based stakeholders

Skills & Expertise Needed

• Agentic AI engineering: building and deploying LLM-powered agents for real business workflows.
• Agent orchestration: designing multi-step and/or multi-agent flows; managing tool use control flow retries and failure handling.
• Agent memory: short-term and long-term memory patterns; conversation state; summarization and context window management.
• Enterprise data access patterns for agents: retrieval/grounding strategies; context assembly from structured and unstructured sources; performance-conscious access.
• Production deployment mindset: security reliability monitoring and maintainability for enterprise-grade AI services.
• Architecture & best practices: ability to design scalable components that fit into an existing framework and can be extended by the team.
• Rapid requirements intake: quickly translating ambiguous reporting/analytics asks into implementable solutions and iterating with stakeholders.
• High autonomy: tech-lead level capability without direct people management; self-directed and able to set engineering direction for the workstream

Good-to-Have Skills

• Experience implementing retrieval-augmented generation (RAG) and hybrid retrieval across structured/unstructured sources.
• Experience with LLMOps practices: prompt/version management automated evaluation and regression testing.
• Experience building observability for AI systems (quality metrics traces latency/cost monitoring).
• Familiarity with Databricks-specific agent or model serving patterns (where applicable).

Experience building lightweight analytics experiences on top of agent outputs (e.g. auto-generated insights/dashboards).