AIML Engineer RAG

Position Overview

We are seeking a hands-on AI/ML Engineer specializing in Retrieval-Augmented Generation (RAG) to design build andoptimizeproduction-grade systems that ground LLM responses in enterprise knowledge. You will own end-to-end retrieval pipelinesfrom ingestion and indexing to hybrid search reranking and evaluationensuring high relevance low latency and measurable reductions in hallucinations and answer failures.

Key Responsibilities

• RAG Pipeline Design & Seeing It Through to Production

• Design and implement robust RAG pipelines: ingestion parsing chunking enrichment embedding indexing retrieval reranking and answer generation.

• Choose and tune retrieval strategies (dense sparse/lexical and hybrid) to maximize recall and precision for real enterprise queries.

• Build citation/grounding mechanisms and response policies to ensure traceable trustworthy outputs.

• Indexing Search Quality & Ranking

• Implement andoptimizevector and hybrid search over structured and unstructured data (documents wikis tickets logs and metadata).

• Develop reranking strategies (cross-encoder late-interaction or LLM-based) and fusion methods (RRF/weighted fusion) to improve ranking quality.

• Establish query understanding and rewriting techniques (intent classification expansions entity/keyword boosting) to improveretrievalrobustness.

• Evaluation Guardrails & Continuous Improvement

• Define anevaluationharness for retrieval and generation using offline datasets and online telemetry (precision/ MRR/nDCGgroundedness).

• Implement automated regression tests and quality gates for new prompts retrievers and model updates.

• Create feedback loops using human review and lightweight labeling to improve relevance over time.

• Performance Reliability & Cost Efficiency

• Optimizelatency and throughput using caching batching streaming responses and efficient retrieval/index configurations.

• Instrument the full pipeline with logs metrics traces dashboards andalerting;triage failures with runbooks.

• Drive cost-aware design across embedding retrieval and generation (token budgets context windows adaptive retrieval).

• Security Access Control & Compliance

• Implement document-level security and access control in retrieval (ACL-aware indexing filtering or query-time authorization checks).

• Ensure safe handling of sensitive data auditability and compliance with enterprise governance standards.

• Collaboration & Enablement

• Partner with domain owners and engineering teams to prioritize use cases and integrate RAG into products and workflows.

• Document best practices and provide reusable templates for ingestion evaluation and deployment.

Required Qualifications

• Bachelors degree in Computer Science Engineering Data Science Human-Computer Interaction or a related field with 5 years of relevant experience; OR a Masters/PhD with 3 years of relevant experience.

• Strong programming skills in Python and experience with LLM/RAG development in production environments.

• Experience with vector databases or search engines and retrieval concepts (ANN indexes BM25/lexical search hybrid retrieval).

• Experience designing evaluation methods for retrieval and LLM outputs (grounding relevance factuality and regression testing).

• Experience building scalable services and APIs (REST/gRPC) with attention to reliability and performance.

• Strong understanding of data processing pipelines metadata design and information retrieval fundamentals.

• Excellent communication skills and ability to work effectively in cross-functional teams.

Preferred Qualifications

• Experience with ranking/reranking techniques (cross-encoders late-interaction learning-to-rank) and fusion methods (RRF weighted scoring).

• Experience with document parsing for PDFs/HTML and handling tables diagrams or mixed layouts.

• Experience with observability and SRE practices for AI systems (SLOs/SLIs incident response runbooks).

• Experience implementing ACL-aware retrieval and security patterns for enterprise knowledge systems.

• Experience building prompt/tooling libraries andmaintainingmulti-model compatibility across LLM providers.

What Success Looks Like (First 6-12 Months)

• A standardized RAG pipeline that measurably improves answer relevance while reducing hallucinations and unresolved queries.

• A repeatable evaluation framework with quality gates that preventsregressionsduring model/retriever/prompt updates.

• Meaningful latency and cost reductions via caching adaptive retrieval and efficient indexing/reranking strategies.

• Secure compliant retrieval that enforces access control without sacrificing search quality.

Note: Technology choices may vary byteamneeds; candidates should be comfortable learning and adapting to new tools.