AI Engineer (Agentic AI / LLM Systems) | Bixware

We’re looking for an engineer who has taken LLM‑powered products from prototype to production. If you’ve built AI agents, retrieval pipelines or memory systems, and you also know how to ship reliable backend services, we’d like to talk.
What we’re looking for
4+ years in software engineering, with at least 1 year building and shipping LLM or GenAI applications.
Strong Python. TypeScript , and SQL Querying.
Hands‑on with LangChain or LangGraph, RAG, MCP and LLM APIs (Anthropic, OpenAI, etc.).
Experience with vector databases such as Qdrant, Milvus, Pinecone, Turbopuffer or pgvector.
Backend depth with FastAPI, Django or Node.js, plus PostgreSQL, MongoDB and Redis, including query and ORM optimization.
Cloud and DevOps on AWS (ECS, S3, RDS, SQS, SNS), GCP or Azure, using Docker and CI/CD.
A record of building integrations with third‑party APIs and platforms.
Nice to have
Contributions to open‑source AI projects such as agent frameworks, memory layers or LLM tools.
Experience at an early‑stage startup or as a founding engineer, owning work end to end.
Exposure to graph databases (Apache AGE, Neo4j) or AI memory and personalization systems.
An ML background with PyTorch or TensorFlow, or research publications.
A B.Tech/B.E. in Computer Science or equivalent from a strong program.
Databricks along with Genie, Azure Synapse along with Co pilot

Work arrangement
No