Source description
About the role
Job Title and Overview We are hiring an AI Agent Developer (Python + GenAI) to design, build, and productionize LLM-powered agents that automate knowledge work and deliver measurable business outcomes. You will work closely with product, data, and platform teams to develop reliable agent workflows (tool-use, planning, retrieval, and evaluation) and deploy them into real customer-facing applications.
Location & Work Mode Work Mode: Remote (work from anywhere). Location: Remote role; no specific city requirement. You will collaborate with a globally distributed engineering team across multiple time zones with overlap hours.
Key Responsibilities
-
Build and iterate on AI agents in Python using modern orchestration frameworks (e.g., LangGraph/LangChain, LlamaIndex, Semantic Kernel) with robust tool-calling and guardrails.
-
Implement Retrieval-Augmented Generation (RAG) pipelines, including chunking strategies, embeddings, vector search, re-ranking, and citation/grounding workflows.
-
Design agent tool interfaces for internal and external systems (REST/gRPC services, SQL databases, SaaS APIs), including auth, retries, idempotency, and rate-limit handling.
-
Develop prompt templates, function-calling schemas, and structured outputs (JSON schema validation) to improve reliability and reduce hallucinations.
-
Set up evaluation and monitoring: offline eval harnesses, golden datasets, A/B prompt tests, and production telemetry (latency, cost, quality, safety signals).
-
Deploy services as containerized microservices (Docker) and support CI/CD, testing, and release processes; optimize inference performance and cost.
-
Collaborate in agile rituals (sprint planning, reviews), contribute to technical design docs, and participate in code reviews to maintain high engineering standards.
-
Ensure security and privacy best practices for LLM apps (PII handling, secrets management, access control, auditability) and implement safety policies and content filtering as needed. Required Skills & Experience
-
2+ years of professional software development experience with strong Python fundamentals (typing, async, packaging, testing).
-
Hands-on experience building with LLMs/GenAI (OpenAI, Azure OpenAI, Anthropic, Google, or open-source models) and understanding of token/cost/latency trade-offs.
-
Experience with RAG and vector databases/search (Pinecone, Weaviate, Milvus, pgvector, Elasticsearch/OpenSearch).
-
API development with FastAPI (preferred) or Flask; ability to design clean interfaces and integrate third-party APIs.
-
Solid grasp of software engineering practices: unit/integration tests (pytest), code quality, version control (Git), and documentation.
-
Familiarity with containers and deployment workflows (Docker, basic Kubernetes or managed cloud services).
-
Working knowledge of databases and data access patterns (PostgreSQL/SQL, caching with Redis). Education & Certifications Bachelor’s degree in Computer Science, Software Engineering, Data Science, or a related field (or equivalent practical experience). Preferred certifications (nice to have): AWS Certified Developer, AWS/Azure AI Engineer, or vendor GenAI credentials (e.g., OpenAI/Azure OpenAI learning paths).
Additional Information You’ll join a product-focused engineering culture that values experimentation, measurable quality, and responsible AI. Benefits typically include flexible remote work, learning budget for GenAI tools/courses, and opportunities to grow into senior IC ownership (agent architecture, evaluation leadership) or technical leadership roles. We encourage open-source contributions and support writing internal design docs and technical demos.
More at Scadea