Job Title

Experience: 6–10 yearsLocation: Mumbai or Bangalore (multi-location team; occasional travel)A hands-on backend engineering role building the core AI/ML-backed systems thatpower BharatIQ’s consumer experiences at scale. This role is not “learn ML on the job.”You must already be effective building and shipping ML-adjacent backend systems(RAG/retrieval, embeddings, ranking, evaluation hooks, feature pipelines) and makingpragmatic tradeoffs across quality, latency, and cost.We cannot upskill on ML fundamentals in this engagement; candidates mustdemonstrate prior delivery of ML-backed backend systems in production.The Engineer will:• Build and operate core backend services for AI product runtime: orchestration,state/session, policy enforcement, tools/services integration• Implement retrieval + memory primitives end-to-end: chunking, embeddingsgeneration, indexing, vector search, re-ranking, caching, freshness and deletionsemantics• Productionize ML workflows and interfaces: feature/metadata services,online/offline parity, model integration contracts, and evaluationinstrumentation• Drive performance and cost optimization (P50/P95 latency, throughput, cachehit rates, token/call cost, infra efficiency) with strong SLO ownership• Add observability-by-default: tracing, structured logs, metrics, guardrail signals,failure taxonomy, and reliable fallback paths• Collaborate with applied ML on model routing, prompt/tool schemas, evaluationdatasets, and release safety gatesWhat we’re looking for (must-have):• 6–10 years building backend systems in production, including at least 2–3 yearson ML/AI-backed products (search, recommendations, ranking, RAG, orassistants)• Practical ML chops: able to reason about embeddings, vector similarity, re-ranking, retrieval quality, evaluation metrics (precision/recall, nDCG, MRR), anddata drift—without needing training• Experience implementing or operating RAG pipelines (document ingestion,chunking strategies, indexing, query understanding, hybrid retrieval, re-rankers)• Strong distributed systems fundamentals: API design, idempotency, concurrency,rate limiting, retries, circuit breakers, and multi-tenant reliability• Comfort with common ML/AI platform components: feature stores/metadata,streaming/batch pipelines, offline evaluation jobs, A/B measurement hooks• Ability to ship end-to-end independently: design → build → deploy → operate ina fast-moving environmentBonus (nice to have):• Agentic runtime / tool-calling patterns, function calling schemas, structuredoutputs, safety/guardrails in production• Prior work with FAISS / Milvus / Pinecone / Elasticsearch hybrid retrieval, andmodel serving stacks• Kubernetes + observability stack depth (OpenTelemetry, Prometheus/Grafana,distributed tracing), plus privacy controls for user data