Senior Software Engineer - Forward Deployed Engineer

Kadencetalent — United States · Posted ~4 hours ago

Senior Full-time Hybrid

Skills

Software engineering LLMs RAG AI agents Python AWS Azure GCP

🔓 Log in to save this job, tailor your resume & track your apply process — 7 days free, no card needed.

Log in to add to target list

Summary ✨ AI‑Generated

Join an AI engineering team building intelligent systems for professional users. You will work directly with customers, develop AI-powered workflows, and deploy advanced solutions into production environments.

Highlights

Work on advanced AI systems, solve complex customer problems, and bring prototypes into production with cutting-edge technologies.

Description

Senior Software Engineer - FDE Forward Deployed Engineer Location: New York City, Dallas, Toronto (Hybrid) The Client: I’m partnering with a global technology leader making a major investment in the next generation of professional AI. This is an opportunity to join one of its flagship AI engineering teams, building agentic systems that are transforming how some of the world’s leading legal organizations work. What makes the opportunity particularly unique is the technology behind it. The organization has developed its own proprietary, domain-specific LLM, trained on decades of authoritative professional data and expert knowledge, while also leveraging leading frontier models within a multi-model AI platform. As part of the Forward Deployed Engineering team, you’ll work directly with customers to take complex problems from prototype through production using LLMs, RAG, agents, and multi-step agentic workflows. The AI platform is already used by more than one million professionals globally, giving engineers the chance to work on cutting-edge applied AI with the data, resources, and scale of a global organization What you’ll be working on: • Building production AI applications using LLMs, RAG, agents, and multi-step agentic workflows • Designing backend systems and APIs primarily in Python • Developing AI solutions for workflows including contract review, litigation, discovery, and regulatory analysis • Building integrations between AI systems, enterprise applications, and proprietary data • Implementing evaluation, observability, monitoring, and quality controls for production AI systems • Working directly with customers and domain experts to translate business problems into technical solutions • Prototyping and evaluating new AI frameworks, models, and approaches as the technology evolves What they’re looking for: • 5+ years of professional software engineering experience • 2+ years building and deploying AI/ML or LLM-powered applications in production • Strong Python and backend engineering experience • Experience with RAG architectures, vector databases, and agentic systems • Familiarity with frameworks such as LangChain, LangGraph, PydanticAI, or AutoGen • Experience with AWS, Azure, or GCP and modern CI/CD practices • Strong system design and distributed systems fundamentals • Comfortable working directly with customers and operating in ambiguous, fast-moving environments This is a great opportunity for an engineer who wants to do more than build AI features—you’ll be close to the end user, solving real problems and taking AI solutions from technical discovery and prototype through production deployment.