Experience: 2-3 years

About Riverfront

Riverfront is building AI governance and evaluation technology for organizations deploying AI agents in the real world. We work on the hard problems that emerge once AI moves beyond prototypes - understanding how agents behave, evaluating them systematically, and helping teams deploy them with greater confidence.

We work in a spec-driven, AI-orchestrated model where the quality of your thinking matters more than your typing speed. We are looking for people who can understand ambiguous problems, make sound technical decisions, and build.

Location: Pune, India/Dubai, UAE The Role

You will own complex problems from brief to delivery - understanding the problem, turning it into a precise spec, making architectural decisions, building alongside the team, and shipping with confidence.

This is a hands-on engineering role with significant ownership.

What You'll Do

- Turn complex product and client requirements into structured technical specs before development begins
- Architect and build agentic AI systems end to end - including RAG pipelines, multi-agent orchestration, MCP-based integrations, tool-use workflows, and memory
- Make architecture decisions across model selection, retrieval strategy, memory design, and orchestration frameworks such as LangGraph, LangChain, Semantic Kernel, CrewAI, and AutoGen
- Own performance and cost trade-offs across token usage, latency, inference quality, and LLM providers including OpenAI, Anthropic, Vertex AI, Azure OpenAI, and AWS Bedrock
- Build observability and evaluation systems using tools such as Langfuse, LangSmith, Helicone, Arize, and W&B;
- Define evaluation criteria and determine what "good" actually means for an AI agent
- Contribute directly to Riverfront's AI governance and evaluation platform
- Participate in solution design, technical decisions, and product delivery




- Review other developers' work and identify weak assumptions or shallow planning early
- Join client and stakeholder conversations when needed and explain technical decisions clearly
- Help evolve the spec-driven development practices the team uses as we scale

What We're Looking For

You have around 2-3 years of hands-on engineering experience, ideally in a product company, technical consultancy, startup, or agency where you have had real ownership.

More importantly, you have shipped AI systems beyond the prototype stage.

You should be comfortable with:

- Agentic and multi-agent AI systems with real tool use and memory
- RAG pipelines and retrieval architecture
- Vector databases such as Pinecone, ChromaDB, Weaviate, Qdrant, or Milvus
- Backend engineering - APIs, microservices, asynchronous systems, Docker/Kubernetes, and CI/CD
- Modern LLM providers and model-selection trade-offs
- AI-assisted development using tools such as Claude Code or Cursor

You have written specs or requirements documents, made architectural decisions, and stood behind them. You are comfortable working directly with product leadership, clients, or other stakeholders rather than operating only from a ticket queue. You ask difficult questions before you start building and document significant decisions as you go.

This role is for someone who wants to stay deeply hands-on - building, experimenting, making technical decisions, and owning outcomes. It is not designed as a short path into people management.

What You'll Get

- Meaningful ownership from day one
- Direct involvement in product and technical decisions
- Work on AI systems that are actually being deployed and evaluated in production
- Exposure across agentic AI, AI governance, evaluation, and enterprise AI
- The opportunity to help shape both the product and the engineering practices behind it
- Competitive compensation based on experience and location

📌 AI Generalist (Pune)
🏢 Riverfront
📍 Pune