Agentic AI Systems
- Discuss this with your agent
- Open in Claude
- Open in ChatGPT
Prepare application
- Draft this with your agent
- Open in Claude
- Open in ChatGPT
Role details
Tech stack
+10 more
Job description
Build production workflows using LLM applications, agents, MCP integrations, APIs, tool calling, RAG, vector search, structured outputs, and multimodal models.
Design agents that reason across enterprise data, tools, and workflows while respecting identity, permissions, policy, and execution controls.
Explore foundation models, model routing, inference, prompt and context engineering, and fine tuning, balancing quality, latency, cost, and reliability.
Develop evaluations covering task success, tool correctness, hallucination detection, regression testing, safety, latency, and cost.
Implement observability, tracing, guardrails, fallback strategies, rate limits, retries, caching, and model gateways for reliable operation.
Improve retrieval, memory, grounding, and context windows through Embedding strategies, embeddings, vector databases, and appropriate enterprise data access.
Secure agent actions through authentication, authorization, secrets management, API access, policy enforcement, human approval, and auditability.
Own architecture, prototypes, integration, debugging, evaluation, and production delivery; feed recurring lessons into platform capabilities, APIs, gateways, identity services, and developer experience.
Requirements
Top Skills & Technologies LLM | MCP | RAG | APIs | Agentic Systems | Vector Database | AI Evaluation | AI Security
Job Summary Thinking Mindsβ client is seeking a hands-on engineer to design, build, and operationalize AI and agentic systems alongside customer engineering teams. This role spans models, inference, tools, context, evaluation, security, observability, and production infrastructure. You will turn ambiguous challenges into working systems and translate recurring customer needs into reusable platform capabilities, reference architectures, and developer workflows.
Ideal Candidate Should Have
Strong engineering fundamentals, technical depth, curiosity, judgment, and end-to-end ownership.
Confidence writing code, debugging agent traces, discussing architecture, and collaborating directly with customer engineers.
An understanding that dependable AI requires systems engineering, data, evaluation, reliability, APIs, and security-not prompts alone.
Comfort experimenting, benchmarking, and shipping while requirements are still evolving., Demonstrated ability to build and troubleshoot software systems with strong engineering fundamentals.
Practical AI fluency and understanding of production reliability, evaluation, context management, and secure tool execution.
Ability to explain architectural tradeoffs and work effectively with AI teams, platform teams, developers, and engineering leaders.
Strong problem-solving skills and willingness to remain close to implementation throughout delivery.
Preferred Qualifications
Background in applied AI, agentic systems, AI infrastructure, distributed systems, developer platforms, security, ML infrastructure, inference, or model platforms.
Experience converting customer-specific solutions into reusable primitives and reference architectures.
Familiarity with retrieval-quality improvements and production agent evaluation frameworks.
Benefits & conditions
Thinking Mindsβ client offers competitive equity, comprehensive medical coverage, flexible PTO, wellness reimbursement, a lunch stipend, and a collaborative engineering environment.
Apply for this position
This job is hosted externally. Click below to view the full posting and apply.
Prepare application
- Draft this with your agent
- Open in Claude
- Open in ChatGPT
Good distractions
Loading talks and stories from around this roleβ¦