Opportunity brief
Overview
We're early-stage and founder-led. Our mission is to deliver AI to industries and businesses where it can help streamline operations and enhance ROI. You'll work alongside the founder on production AI systems shipped to early customers.
Responsibilities
- Application Development: Build and maintain components of our app and orchestration layers for agentic AI apps, including tool routing, structured outputs, schema-validated generation, and prompt versioning. Required skills: Python, Fastify, Next.js, Express.js, GCP/AWS.
- Retrieval Engineering: Implement and tune RAG pipelines over operational data. Measure retrieval quality using evaluation metrics.
- Evaluation Infrastructure: Build golden sets, regression harnesses, and LLM-as-judge frameworks.
- Observability & Telemetry: Instrument latency, cost, and quality metrics per LLM call. Trace failures end-to-end.
- Integration Support: Contribute to tools, MCPs, connectors, and ingestion pipelines, including FastAPI services, async workers, and event handling.
- Documentation: Maintain technical documentation for every component you ship, readable by engineers who join the project.
- Code Review Participation: Review peer PRs, defend your own, and take feedback that makes the system better.
Skills Required
Must Have
- Strong Python skills with hands-on experience in async patterns
- FastAPI or an equivalent Python web framework
- At least one shipped end-to-end LLM project with RAG, an agent, fine-tuning, or an applied ML system
- Working knowledge of vector databases such as Qdrant and pgvector, and embedding models
- Familiarity with at least one orchestration framework such as LangChain or LangGraph
- Fluency in Git, Docker, and Linux
- Ability to read and research technical papers
Good to Have
- Open-source contributions of any scale
- TypeScript or Next.js for cross-stack work
- Cloud exposure — AWS (Lambda, ECS, RDS), GCP (Cloud Run, BigQuery), or Firebase
- Distributed systems or event-driven architecture background
- Fine-tuning, PEFT, or domain-adaptation experience
- Exposure to or rankings in competitive programming or competitions such as GSoC
- Exposure to enterprise software environments such as ERP, CRM, or ticketing systems
Eligibility
- Final-year BTech students, recent graduates, or Master's students in CS, AI, or a related field
- Available 30–40 hours per week for a minimum 2-month commitment
Engagement Structure
- Mode: Remote
Compensation
Compensation is project/milestone-based, structured as follows:
- Each engagement window, typically 4–6 weeks, is scoped into clearly defined deliverables agreed upon in writing before work begins.
- Each milestone carries a fixed payout, released upon completion and sign-off.
- Performance bonuses are available for exceptional delivery, including early completion, exceeding scope, or measurable production impact.
- Compensation is benchmarked against the Indian AI internship market and adjusted at intake based on skill depth and prior production experience. Candidates should keep in mind that Operonn is in its foundational early stage when communicating their expectations.