AI/ML Engineer (LLM + AWS + Agents)
We’re looking for a senior AI/ML Engineer (or Tech Lead) with strong experience building production LLM systems, agent workflows, and AWS-native architectures.
You will design and implement Veruno.AI’s core AI platform: Discovery Agent, analysis workflows, ingestion pipelines, vector search, and multi-LLM orchestration.
Responsibilities:
- Build AI agents (structured interviews, multi-step analysis, JSON-mode).
- Implement multi-LLM routing (Bedrock, OpenAI).
- Create ingestion pipelines: website crawling, LinkedIn, docs.
- Build RAG pipelines, chunking, embeddings, pgvector/OpenSearch search.
- Design AWS serverless backend (API Gateway, Lambda, Step Functions, DynamoDB, S3).
- Implement guardrails, retries, JSON schemas, cost tracking.
- Create Terraform templates & automation “solution packs.”
- Generate PDF reports via Lambda (headless browser).
Requirements:
- 3+ years building production LLM/AI systems.
- Strong with Bedrock (Claude/Llama/Mistral) + OpenAI API.
- Experience with agent frameworks (LangChain/LangGraph) or Step Functions workflows.
- RAG expertise (full pipeline).
- Strong AWS serverless: Lambda, Step Functions, DynamoDB, S3, IAM, Secrets Manager.
- TypeScript/Node.js or Python.
- Strong understanding of security, IAM, KMS, observability.
Required languages
| English | B2 - Upper Intermediate |
Bedrock, LangChain, RAG, LLM/Llama/Mistral/GPT/RAG/FAISS
📊
Average salary range of similar jobs in
analytics →
Loading...