Staff Solutions Engineer

As a Staff Solutions Engineer, you will play a strategic, hands-on role in transforming JazzX’s AGI platform into scalable, high-impact solutions for enterprise customers. With your deep technical expertise and leadership, you’ll drive the design, development, and deployment of LLM-powered applications across complex client environments.

You will:

• Lead the integration of LLM features, vector search pipelines, and agentic workflows into production systems.
• Partner with solution architects, product managers, and customer success teams across the full solution lifecycle—from discovery through deployment and optimization.
• Influence core platform enhancements by contributing real-world learnings and reusable components.
• Set the technical bar through design leadership, mentoring, and rigorous engineering practices.

• Architect and implement end-to-end AGI solutions, including retrieval-augmented generation (RAG), tool-using agents, and LLM orchestration patterns.
• Design and integrate secure data pipelines, APIs, and authorization layers tailored to customer environments.
• Make high-impact, component-level design decisions, balancing performance, maintainability, and customer goals.

• Own delivery of proof-of-concepts, pilots, and scalable production rollouts in agile settings.
• Ensure production readiness through observability (logs, metrics, tracing) and contribute to incident response/on-call rotations as needed.

• Work closely with research and product teams to test and validate emerging LLM techniques in customer contexts.
• Serve as a technical escalation point for customer implementations, proactively identifying and resolving complex issues.
• Mentor junior engineers and contribute to internal best practices through code reviews, demos, and documentation.

• Evaluate and pilot emerging frameworks (e.g., AutoGen, LangGraph, WASM inference engines) and contribute reusable assets to the internal platform.
• Shape JazzX’s field engineering playbook by sharing insights, reusable templates, and domain-specific solutions.

• 8+ years of experience in professional software engineering, with at least 3+ years working on ML, data, or AI/LLM-centric systems.
• Strong expertise in Python (or Go/Java), with production-grade coding, testing, and CI/CD best practices.
• Proficiency in modern GenAI/LLM frameworks (e.g., LangChain, LlamaIndex, HuggingFace Transformers, PyTorch, TensorFlow) and vector databases (e.g., Pinecone, Weaviate, FAISS).
• Familiarity with integrating REST/GraphQL APIs, Kafka streams, and relational/non-relational databases.
• Excellent communication skills and the ability to work cross-functionally with engineering, product, and customer stakeholders.
• Willingness to travel up to 20% for key customer engagements.

• Experience delivering RAG, fine-tuning, or agentic solutions in regulated industries (e.g., finance, healthcare, telecom).
• Any Certifications in cloud
• Exposure to MLOps and data engineering tools (e.g., MLflow, Kubeflow, Vertex AI, Airflow, dbt).

• Technical Leadership – You take ownership, guide architecture decisions, and raise the bar for engineering quality.
• Customer Focus – You thrive on solving real-world challenges and building trust with technical stakeholders.
• Startup Mindset – You move fast, embrace ambiguity, and iterate quickly.
• Collaboration & Mentorship – You elevate those around you through thoughtful feedback, knowledge sharing, and support.
• Mission-Driven – You’re motivated by the opportunity to shape the future of intelligent, human-centric software.