About the role
Role & responsibilities
Technical Skills:
• Advanced proficiency in Python.
• Extensive experience with LLM frameworks (Hugging Face Transformers, LangChain) and prompt engineering techniques
• Experience with big data processing using Spark for large-scale data analytics
• Version control and experiment tracking using Git and MLflow
• Software Engineering & Development: Advanced proficiency in Python, familiarity with Go or Rust, expertise in microservices, test-driven development, and concurrency processing.
• DevOps & Infrastructure: Experience with Infrastructure as Code (Terraform, CloudFormation), CI/CD pipelines (GitHub Actions, Jenkins), and container orchestration (Kubernetes) with Helm and service mesh implementations.
• LLM Infrastructure & Deployment: Proficiency in LLM serving platforms such as vLLM and FastAPI, model quantization techniques, and vector database management.
• MLOps & Deployment: Utilization of containerization strategies for ML workloads, experience with model serving tools like TorchServe or TF Serving, and automated model retraining.
• Cloud & Infrastructure: Strong grasp of advanced cloud services (AWS, GCP, Azure) and network security for ML systems.
• LLM Project Experience: Expertise in developing chatbots, recommendation systems, translation services, and optimizing LLMs for performance and security.
• General Skills: Python, SQL, knowledge of machine learning frameworks (Hugging Face, TensorFlow, PyTorch), and experience with cloud platforms like AWS or GCP.
• Experience in creating LLD for the provided architecture.
• Experience working in microservices based architecture.
Domain Expertise:
• Deep understanding of ML and LLM development lifecycle, including fine-tuning and evaluation
• Expertise in feature engineering, embedding optimization, and dimensionality reduction
• Advanced knowledge of A/B testing, experimental design, and statistical hypothesis testing
• Experience with RAG systems, vector databases, and semantic search implementation
• Proficiency in LLM optimization techniques including quantization and knowledge distillation
• Understanding of MLOps practices for model deployment and monitoring
Professional Competencies:
• Strong analytical thinking with ability to solve complex ML challenges
• Excellent communication skills for presenting technical findings to diverse audiences
• Experience translating business requirements into data science solutions
• Project management skills for coordinating ML experiments and deployments
• Strong collaboration abilities for working with cross-functional teams
• Dedication to staying current with latest ML research and best practices
• Ability to mentor and share knowledge with team members
- AI Engineer (Agentic App Experience / LLM Integration)
Summary: Engineer focused on delivering application features powered by
agentic workflows, integrating with MLOps-managed agents, consuming LLM
capabilities via an AI Gateway, and shipping reliable production experiences.
Responsibilities
• Build app-facing AI features that consume agentic workflows exposed by
MLOps platforms
• Integrate LLM capabilities via AI Gateway (routing, auth, policy controls,
logging)
• Implement orchestration patterns: tool/function calling, context handling,
prompt/version management
• Ensure production readiness: latency optimization, evals, guardrails,
monitoring, and incident support
• Partner with security/compliance and platform teams to meet governance
and data controls
Must Have
• Experience building production AI integrations (LLMs, agents/orchestration,
APIs)
• Strong engineering fundamentals: testing, observability, reliability, secure
integration
• Familiarity with prompt/versioning, evaluation methods, and safety/quality
controls
Preferred candidate profile
GenAI / LLM Engineers
(Python, FastAPI, Microservices, K8s, RAG, VectorDBs)
LLMs, agents/orchestration, APIs, AI integrations, Prompt/versioning
Millions of jobs, with real people getting hired every day
Questions, answered
Click "Apply with JobAssist" – we tailor your resume and application to this role and submit it for your approval.
Yes. This role at SP Software was screened before publishing – we confirmed the employer before listing it.
The employer didn't disclose a salary range for this listing. JobAssist shows pay whenever it's available.
This position can be done from anywhere, with no in-office requirement.
Yes – every application is tailored from your profile and this job's requirements, and you can review and edit before it's sent.