Work authorization: Authorized to work in the US (F-1 OPT, STEM-eligible)
Software engineer and AI engineer. 2 years full-time on a Java / Spring Boot B2B platform, then an MS at Northeastern. Looking for full-time Software Engineer, AI Engineer or Forward Deployed Engineer roles.
Recent work:
- OpenCodeIntel (https://opencodeintel.com): code search for AI coding agents. Web app, REST API and a 12-tool MCP server; 94% Hit@1 across 14 open-source codebases on a 665-query research eval. Solo, MIT.
- Overhear (https://github.com/DevanshuNEU/overhear): grades every call a voice agent takes against the clinic's database. Code decides the facts, an LLM judge scores the rest; caught 23 of 23 planted failures on a 39-call golden set.
- CallBudget (https://github.com/DevanshuNEU/callbudget): a voice agent that finds scarce drugs in fewer calls (4.3 to 2.3 expected) and abstains instead of guessing (false "in stock" 10% to 0%, simulated pharmacist on real data).
- Saar (https://getsaar.com): Chrome extension on the Web Store that meters Claude.ai tokens and cost, entirely client-side.
Founder & CEO, OpenCodeIntel - Building the context layer for AI coding agents. We do semantic code search + dependency graph analysis, serve it via MCP so Cursor/Windsurf/Claude write code that actually fits your codebase. 87.5% Hit@1 retrieval accuracy. Landing page live, waitlist open.
Shipped: GitHub OAuth repo import, dependency visualization, full MCP integration, vector search with OpenAI embeddings.
Previous: 2 yrs full-stack @ Jaksh Enterprise - 65% API latency reduction, AWS migration, CI/CD from scratch.
MS Software Engineering @ Northeastern (May 2026). OPT = 3 years work auth, no lottery.
Looking for: Full-time SWE at early-stage startups in dev tools / AI infra / code intelligence. Also open to conversations about OpenCodeIntel.
Remote: Yes (US)
Willing to relocate: Yes, anywhere in the US
Technologies: Python, TypeScript, Java, Go, SQL, FastAPI, Spring Boot, Node.js, React/Next.js, Postgres, Redis, Pinecone, AWS, Terraform, Docker, Kubernetes, CI/CD, MCP servers, RAG, LLM evals (LLM-as-a-judge), voice agents (Pipecat, Deepgram, Retell), Claude and OpenAI APIs
Résumé/CV: https://www.devanshuchicholikar.com/resume
Email: [email protected]
GitHub: https://github.com/DevanshuNEU
Work authorization: Authorized to work in the US (F-1 OPT, STEM-eligible)
Software engineer and AI engineer. 2 years full-time on a Java / Spring Boot B2B platform, then an MS at Northeastern. Looking for full-time Software Engineer, AI Engineer or Forward Deployed Engineer roles.
Recent work:
- OpenCodeIntel (https://opencodeintel.com): code search for AI coding agents. Web app, REST API and a 12-tool MCP server; 94% Hit@1 across 14 open-source codebases on a 665-query research eval. Solo, MIT.
- Overhear (https://github.com/DevanshuNEU/overhear): grades every call a voice agent takes against the clinic's database. Code decides the facts, an LLM judge scores the rest; caught 23 of 23 planted failures on a 39-call golden set.
- CallBudget (https://github.com/DevanshuNEU/callbudget): a voice agent that finds scarce drugs in fewer calls (4.3 to 2.3 expected) and abstains instead of guessing (false "in stock" 10% to 0%, simulated pharmacist on real data).
- Saar (https://getsaar.com): Chrome extension on the Web Store that meters Claude.ai tokens and cost, entirely client-side.