Gohighlevel2mo ago

Application Engineer II

IndiaRemoteEE Full-Timemid

EngineeringApplication Engineer

1 views0 saves0 applied

Apply Now

Quick Summary

Key Responsibilities

- Design, implement, and iterate on LangGraph workflows that support structured

Technical Tools

EngineeringApplication Engineer

About us
HighLevel is an AI-powered business operating system that gives agencies, entrepreneurs and SMBs the infrastructure to build, automate and scale. Today, HighLevel supports SMBs across 150+ countries, fueling community-driven growth rooted in real customer outcomes.
To date, businesses operating on HighLevel have generated over $7 billion in ecosystem value, demonstrating the impact of shared infrastructure at scale. By centralizing conversations, automation and intelligence into one system, we help businesses move faster, reduce complexity and execute efficiently.
Behind the platform, HighLevel powers more than 4 billion API hits and 2.5 billion message events daily. With 250 terabytes of distributed data, 250+ microservices and over 1 million domain names supported, our architecture is built for performance, resilience and long-term scalability.

Our people
With over 2,000 team members across 10+ countries, HighLevel operates as a global, remote-first organization built for speed and ownership. We value initiative, clarity and execution, creating space for ambitious people to build systems that support millions of businesses worldwide. Here, innovation thrives, ideas are celebrated and people come first, no matter where they call home.

Our impact
Every month, HighLevel enables more than 1.5 billion messages, 200 million leads and 20 million conversations for the more than 1 million businesses we support. Behind those numbers are real people building independence, expanding opportunity and creating measurable impact. We’re proud to be a part of that.
Learn more about us on our YouTube Channel or Blog Posts

Who You Are:

You are an AI-focused software engineer with strong backend fundamentals and hands-on experience delivering LLM-enabled applications. You have delivered production systems and apply a reliability-first approach across agentic orchestration and applied AI pipelines. You operate with increasing autonomy on well-scoped problems, while collaborating closely with senior engineers on system design, architecture decisions, and long-term technical direction.

You have hands-on experience implementing LangGraph workflows in production environments. You can take a workflow from vague intent to a shippable service with clear contracts, guardrails, evaluation, and observability.

You operate effectively in cross-functional delivery environments. You can partner directly with Business Analysts and org leaders to clarify outcomes, translate business needs into acceptance criteria, and communicate tradeoffs without getting stuck in ambiguity. You bring delivery discipline, iterate efficiently, and focus on measurable outcomes.

You apply a production engineering mindset. You build AI systems that are adopted in day-to-day operations, with monitoring, cost controls, and reliability built into the implementation.

What You’ll Be Doing:

- Design, implement, and iterate on LangGraph workflows that support structured requirement capture, clarification loops, stateful routing, and tool orchestration.

- Build reusable workflow components (nodes, validators, schema-enforced outputs, guardrails) and standard patterns for retries, fallbacks, and human-in-the-loop review where appropriate.

- Implement robust tool execution patterns (timeouts, error taxonomy, idempotency where needed) and ensure safe, deterministic structured outputs for downstream automation.

- Partner with Business Analysts and org leaders during discovery and refinement to clarify goals, constraints, and success metrics; translate requirements into sprint-ready tickets and acceptance criteria.

- Build and maintain agent-callable services/APIs for Snowflake retrieval, operational actions (e.g., Slack/workflows), and data enrichment/packaging.

- Establish evaluation and observability for agent workflows (golden cases, regression suites, tool mocks; latency/cost/error monitoring) and contribute to pragmatic SLOs.

- Contribute to our in-house transcription application through agent adjustments and infrastructure improvements, including transcript ingestion, normalization (timestamps/speaker turns/metadata), storage, and retrieval surfaces for downstream tooling.

- Improve reliability of transcription pipelines through queue/worker architectures, retries/backoff, idempotency, and replay tooling.

- Implement and iterate on rubric-based call scoring (versioned rubrics, explainable outputs, calibration support) and publish scoring artifacts that are usable for coaching and operational workflows.

- Implement streaming considerations where applicable (session handling, backpressure/reconnect patterns) and ensure clean handoffs between capture, transcription, and scoring stages.

- Deliver scoped components and workflows with guidance on architecture and design decisions from senior engineers or tech leads.

What You’ll Bring:

- 3–6 years of software engineering experience (backend/services preferred).

- LangGraph experience is required (demonstrated implementation of real workflows).Strong proficiency in Python and/or TypeScript, including API/service design.

- Experience building production services in a compiled, runtime-stable language (e.g., Go) for high-throughput, low-latency workloads (streaming I/O, async workers, and media/transcription pipelines).

- Strong SQL skills; comfort working with warehouse-backed applications (Snowflake preferred).

- Practical experience shipping LLM applications:

- tool/function calling, structured outputs, and schema validation

- retrieval patterns (RAG), routing, and context management

- prompt/version management and evaluation methodologies

- Production engineering fundamentals:

- retries/idempotency, async job patterns, monitoring, and cost controls

- Strong communication and stakeholder partnership skills:

- ability to lead technical discovery conversations

- ability to translate business intent into acceptance criteria and implementation plans

- Botpress or similar agent builders (agent authoring and tool packaging).

- Streaming systems exposure (WebSockets / HTTP2), backpressure + reconnect logic.