Bima P.

I build AI agents and LLM powered systems that run in production, not just in demos Most of my day today is spent on an agentic AI platform at a UK AI startup. I work on multi-agent workers, tool calling, orchestration, usage and billing, and the infrastructure underneath it, mostly in Rust A lot of teams come to me with a prototype that works on a laptop but falls apart with real users. Answers drift, costs spike, agents get stuck in loops, and nobody can tell what went wrong. I step in, find where it breaks, and make it stable enough to ship What I typically help with - AI agents and multi-agent workflows that call real tools and APIs - LLM integration with OpenAI, Anthropic, and open source models - RAG pipelines, embeddings, and vector search - Agents that take real actions such as purchasing, booking, or filling forms - AI automation with n8n, Azure Functions, and custom backends - Data pipelines that feed AI using Databricks, PySpark, and Azure - Guardrails, evaluation, cost control, and observability for LLM apps - Rust and Python backends built for low latency and high load Background 7+ years in software engineering across fintech, trading systems, energy, and enterprise. I have also built low-latency trading bots in Rust and Web3 systems on Cosmos SDK, Solana, and EVM, so I am comfortable where AI meets payments and onchain systems Core stack Rust, Python, TypeScript, OpenAI, Anthropic, RAG, vector databases, Azure, Databricks, Docker, Kubernetes, Prometheus, Grafana If you have an AI idea or a prototype that needs to become a real product, send me a message and we can figure out the fastest path to get it live