In this role, you will design, build, deploy, and operate Generative AI solutions end to endLLM-powered applications, retrieval-augmented generation (RAG), and agentic workflowsintegrated with enterprise data and systems.

Youll collaborate with product, engineering, and security partners to deliver reliable, scalable, and safe GenAI capabilities, with strong focus on evaluation, observability, and cost/latency performance in production.

What Youll Do :

- Design and implement LLM-powered conversational experiences (chat assistants/copilots), integrating tools, APIs, and enterprise data sources.

- Build and productize RAG pipelines (document ingestion, chunking, embeddings, indexing) using vector databases and AI-enabled search.

- Engineer scalable LLM inference and orchestration (prompt templates, function/tool calling, streaming, caching) with clear SLOs for latency and reliability.

- Partner with product and engineering teams to translate business requirements into model specifications and system designs.

- Implement safety and compliance guardrails (content filtering, prompt injection defenses, data access controls) and support red-teaming/testing of GenAI applications.

- Optimize GenAI solutions for cost and performance (token usage, prompt compression, caching, model routing) while maintaining response quality.

- Apply Responsible AI practices for GenAI (grounding, hallucination mitigation, privacy-by-design, bias/toxicity evaluation) and align with security requirements.

- Document architectures, promptbooks, evaluation results, and operational runbooks; build reusable components to enable team scalability.

Qualifications :

- BE/BTech in Computer Science, Data Science, Engineering, or a related field (or equivalent practical experience).

- 7+ years of total experience as a software engineer, including hands-on experience building and productionizing AI/ML and GenAI solutions (LLMs, RAG, prompt/tool calling) using Python, Golang, Bash, Node, React Terraform, gRPC, Git, GitLab, Docker, Argo, Kubernetes.

- Strong programming skills in Python (preferred)/Golang and experience building LLM applications using common frameworks (e.g., LangChain, LlamaIndex, Semantic Kernel); familiarity with evaluation/testing frameworks is a plus.

- Experience deploying and operating GenAI applications on cloud platforms (GCP/Azure/AWS), including integration with managed LLM services and secure API patterns.

- Experience with vector databases and retrieval systems (e.g., Pinecone, Milvus, Weaviate, Elasticsearch/OpenSearch) and LLMOps tooling for prompt/version management and evaluation.

- Knowledge of CI/CD and observability for GenAI systems (quality/safety metrics, tracing, monitoring latency and cost, incident response).

- Working knowledge of Agile delivery and collaboration tools (e.g., Jira, Confluence); ability to communicate technical trade-offs to stakeholders.

- Strong analytical and systems-thinking skills to diagnose GenAI issues (grounding gaps, hallucinations, prompt injection, retrieval quality) across app, data, and infrastructure layers.

We flex our time together, collaborating remotely and in-person to empower our teams to work in the ways that work best for them.

Your Security Matters :

- Our candidates personal information and online safety are top of mind for us.