Sr. Software Engineer (AI, ML, Python, LLM, Langchain) - Locals Only - Job#3619664

Sr. Software Engineer (AI, ML, Python, LLM, Langchain)

• Locals Only
• Job#3619664 at Pave Talent Sr. Software Engineer (AI, ML, Python, LLM, Langchain)
• Locals Only
• Job#3619664 at Pave Talent in Redwood City, California Posted in about 14 hours ago.

Type:

full-time

Job Description:

????????????'???????? ???????????????????? ???????? ???????????????????????????? ???????????????? ???????????????? ???????? ????????????????????????????????????????. ???????????? ???????????????????? ???????????? ???????????????? ???????????????????? ???????????? ????????????????????. Pave Talent is recruiting on behalf of a commercial-stage autonomous mobility company making the leap from R D into live service. The AI systems you build here won't be demos or internal tools. They'll power a fleet in the real world, interacting with real customers, in real time. This is a contract role paying $97 to $102 per hour, on-site five days a week at Foster City CA through June 2026, with strong conversion potential as the company scales. ???????????? ???????????????????????????? ????????????????

• You've shipped AI agents or retrieval-augmented generation (RAG) systems into production and have the scars to prove it
• You think in systems: embeddings, vector stores, prompt chains, model evaluation, latency trade-offs
• You're energized by ambiguity. This company is scaling fast and the roadmap evolves quickly
• You want to be in the room where architecture decisions get made, not handed a spec to implement
• You're comfortable owning reliability and performance, not just handing off to DevOps This role is NOT a good fit if you prefer a fully defined backlog, a slow enterprise release cycle, or want to stay in research without shipping.

???????????? ???????????????????????????????????????????? You'll join a cross-functional engineering team at the exact moment the company transitions from building to operating. The AI work here spans the full stack of what modern applied AI looks like: autonomous decision-making agents, conversational interfaces for customer service, RAG pipelines that pull from live operational data, and large language model (LLM) deployments balanced for cost, latency, and accuracy in a real fleet environment. ???????????????? ????????????'???????? ????????????????????

• Design and deploy AI agents and autonomous systems capable of multi-step task execution and real-time decision-making
• Build conversational AI solutions including chatbots and voice-based customer service systems integrated into fleet operations
• Develop and optimize RAG systems: vector databases, embedding strategies, retrieval pipelines, and prompt engineering
• Implement and tune machine learning models using PyTorch, balancing accuracy, latency, and cost for production use
• Evaluate and deploy LLMs from providers including OpenAI, Anthropic, Google, and Meta based on application-specific requirements
• Build AI-powered integrations across services using REST APIs, gRPC, or event-driven architectures (Kafka)
• Architect production-grade AI systems with reliability, observability, and scalability built in from the start
• Collaborate with product, data, and platform teams to translate commercial requirements into technical solutions ???????????????????????????????????????????????????????? ????????????????????????????????:
• 6+ years of Python development with a focus on AI or machine learning applications
• Hands-on production experience with

PyTorch:

model training, fine-tuning, or deployment

• Direct experience building or operating RAG systems: vector databases, embeddings, retrieval strategies, and prompt engineering
• Familiarity with AI agent frameworks (LangChain, LlamaIndex, AutoGen, or similar)
• Working knowledge of transformer architecture and attention mechanisms
• Experience integrating AI capabilities into applications via REST APIs, gRPC, or Kafka
• Ability to work on-site in San Diego five days per week ???????????????????? ????????????????????????:
• Proficiency in Kotlin and full-stack development experience
• Cloud deployment experience on AWS, GCP, or Azure, especially microservices
• Containerization and orchestration with Docker and Kubernetes
• CI/CD pipeline experience and DevOps practices in an AI systems context
• Prior experience in autonomous vehicles, robotics, or mobility tech ?

??????????????????????????????????????????????? ???????????? ???????????????????????????????? ???????????????????????? ????????????????: $97 to $102 per hour ????????????????????????????????: Monday through Friday, standard business hours ????????????????????????????????????: On-site, Foster City CA ???????????????????????????????????????? ????????????????????????: Contract through June 30, 2026 ????????????????????????????????????????: Not guaranteed per this listing, but the company is in active growth mode Apply via and we'll reach out to schedule a conversation. Confidential search; your application is fully private. ???????????????? ???????????????????????? | ???????????????????????? ????????????????????????????????????????