TechGrove is the **Centre of Excellence** for Banyan Software, based in Chennai, India. It plays a key role in supporting Banyan’s global businesses through technology, security, and software development. TechGrove brings together India’s deep pool of technical talent with Banyan’s long-term approach to growth, creating a trusted, developer-focused environment where people can do their best work. **Senior AI / RAG Engineer — Applied LLM & Retrieval** This is a deeply hands-on role for an experienced engineer who wants to spend their time building. A big part of the job is growing our fleet of AI sub-agents — designing new specialized agents and wiring them into complete, end-to-end multi-agent agentic workflows and architecture. You'll design, implement, and harden our RAG, agent, and LLM features end-to-end — the retrieval pipelines, the agent orchestration, the model-gateway routing and fallback logic, the AI automation pipelines, and the evaluations that keep quality high — all inside a GDPR-first, EU-only data boundary. Your work ships to production and you own it through to it working reliably. What you'll do - Grow our fleet of AI sub-agents — design and build more and more specialized agents, and wire each into a complete multi-agent, agentic AI-driven workflow and architecture, from single-purpose agents up to orchestrated end-to-end flows. - Build and improve RAG pipelines — chunking, embeddings, vector storage and retrieval, re-ranking, grounding and citation — over proprietary data such as work orders, rate cards, and uploaded documents. - Build LLM features on cloud-hosted large language models — classification, extraction, summarisation, structured/JSON output, prioritisation, and multimodal (text + image) reasoning — from prototype through to production. - Extend the internal Model Gateway — task/tier model routing, retries, fallback, cost estimation, and per-tenant usage limits. - Build adversarial validation agents — AI agents that critique and stress-test model outputs, plans, and designs over multiple rounds to catch errors and edge cases before they ship. - Design and build AI automation pipelines — orchestrated, repeatable AI workflows, both in the product and across our engineering process. - Automate the SDLC with AI — bring AI into how we plan, generate, review, test, and ship code, and build the tooling that makes it repeatable. - Integrate and extend an automated testing framework — including AI-assisted test generation and self-checking pipelines for our AI features. - Build the evaluations — datasets and harnesses that measure accuracy, faithfulness/hallucination, latency, and cost, and catch regressions in non-deterministic systems before release. - Do the prompt engineering — schema-validated outputs, tool/function calling, and the tuning needed to reduce hallucination and hit quality targets. - Enforce data-protection by design — tenant-scoped retrieval, PII handling, and erasure/cascade in the retrieval layer; keep every data flow inside the EU/EEA. - Ship to production on AWS (Python, ECS) with proper observability, and own your features through to reliable operation. Required skills & experience *All of the following are required.* - 5–8+ years of software engineering, with deep, production-grade Python. - Substantial hands-on experience building and shipping LLM-powered systems to production — you've taken more than one from idea to reliable, scaled feature and stayed close to the code. - Designing and composing multi-agent systems — building specialized sub-agents and wiring them into complete, end-to-end agentic workflows and architecture. - Deep RAG expertise — embeddings, vector stores (e.g. pgvector, OpenSearch, Pinecone, FAISS), semantic search, chunking strategies, re-ranking, grounding — and the judgement to know what actually moves quality. - Embeddings at scale and multilingual retrieval. - Advanced prompt engineering and structured output / tool use / function calling with schema-validated (JSON) responses; strong instincts for reducing hallucination. - Deep experience with cloud-hosted commercial LLM APIs / a managed LLM platform. - Agentic / multi-agent frameworks (LangGraph, LangChain, or similar) — orchestration and state machines — including building adversarial / validation agents or LLM-as-judge setups. - AI-driven SDLC automation and experience building AI automation pipelines (CI/CD or workflow orchestration). - Integrating automated testing frameworks and AI-assisted test automation. - Proven ability to build evaluations for AI systems — datasets, metrics (accuracy, faithfulness, latency, cost), and regression testing. - Real command of cost/latency trade-offs — model tiering, routing, fallback, and caching — at production scale. - Strong AWS background — building, deploying, and operating services in production; IAM and region-aware design. - Streaming, latency optimisation, and prompt caching. - Vector-DB operations, observability (Datadog / CloudWatch), and IaC. - GDPR / data-residency / responsible-AI experience — no-training commitments, tenant isolation, DPAs, PII minimisation. - Experience with AI systems running at production scale. - Excellent testing discipline, code quality, and engineering judgement; comfortable owning a feature end-to-end. ***Beware of Recruitment Scams*** We have been made aware of individuals fraudulently posing as members of our Talent Acquisition team and extending fake job offers. These scams may involve requests for personal information or payment for equipment. **Protect yourself by following these steps:** - Verify that all communications from our recruiting team come from an **@banyansoftware.com** email address. - Remember, employers will **never** request payment or banking information during the hiring process. - If you receive a suspicious message, **do not respond** — instead, forward it to careers@banyansoftware.com and/or report it to the platform where you received it. Your safety and security are important to us. Thank you for staying vigilant.