Staff / Senior AGI Solutions Engineer

Job Title: Senior AGI Engineer – GTM Solution Delivery 

Role Overview 

As a Senior AGI Engineer you are the hands-on technical force that turns JazzX’s AGI platform into working, measurable solutions for customers. You will: 

• Build and integrate LLM-driven features, vector search pipelines, and tool-calling agents into client environments. 

• Collaborate with solution architects, product, and customer-success teams from discovery through production rollout. 

• Contribute field learnings back to the core platform, accelerating time-to-value across all deployments. 

You are as comfortable writing production-quality Python as you are debugging Helm charts, and you enjoy explaining your design decisions to both peers and client engineers. 

Key Responsibilities 

Focus Area 

What You’ll Do 

Solution Implementation 

* Develop and extend JazzX AGI services (LLM orchestration, retrieval-augmented generation, agents) within customer stacks. 
* Integrate data sources, APIs, and auth controls; ensure solutions meet security and compliance requirements. 
* Pair with Solution Architects on design reviews; own component-level decisions. 

Delivery Lifecycle 

* Drive proofs-of-concept, pilots, and production rollouts with an agile, test-driven mindset. 
* Create reusable deployment scripts (Terraform, Helm, CI/CD) and operational runbooks. 
* Instrument services for observability (tracing, logging, metrics) and participate in on-call rotations. 

Collaboration & Support 

* Work closely with product and research teams to validate new LLM techniques in real-world workloads. 
* Troubleshoot customer issues, triage bugs, and deliver patches or performance optimisations. 
* Share best practices through code reviews, internal demos, and technical workshops. 

Innovation & Continuous Learning 

* Evaluate emerging frameworks (e.g., LlamaIndex, AutoGen, WASM inferencing) and pilot promising tools. 
* Contribute to internal knowledge bases and GitHub templates that speed future projects. 

Qualifications 

Must-Have 

• 5+ years of professional software engineering experience; 2+ years working with ML or data-intensive systems. 

• Proficiency in Python (or Java/Go) with strong software-engineering fundamentals (testing, code reviews, CI/CD). 

• Hands-on experience deploying containerised services on AWS, GCP, or Azure using Kubernetes & Helm. 

• Practical knowledge of LLM / Gen-AI frameworks (LangChain, LlamaIndex, PyTorch, or TensorFlow) and vector databases. 

• Familiarity integrating REST/GraphQL APIs, streaming platforms (Kafka), and SQL/NoSQL stores. 

• Clear written and verbal communication skills; ability to collaborate with distributed teams. 

• Willingness to travel 10–20 % for key customer engagements. 

Nice-to-Have 

• Experience delivering RAG or agent-based AI solutions in regulated domains (finance, healthcare, telecom). 

• Cloud or Kubernetes certifications (AWS SA-Assoc/Pro, CKA, CKAD). 

• Exposure to MLOps stacks (Kubeflow, MLflow, Vertex AI) or data-engineering tooling (Airflow, dbt). 

Attributes 

• Empathy & Ownership: You listen carefully to user needs and take full ownership of delivering great experiences. 

• Startup Mentality: You move fast, learn quickly, and are comfortable wearing many hats. 

• Detail-Oriented: You care about the little things  

• Mission-Driven: You want to solve important, high-impact problems that matter to real people. 

• Team-Oriented: Low ego, collaborative, and excited to build alongside highly capable engineers, designers, and domain experts. 

Travel 

This position requires the ability to travel to client sites as needed for on-site deployments and collaboration. Travel is estimated at approximately 20–30% of the time (varying by project), and flexibility is expected to accommodate key client engagement activities.